Llama 3 6B V0.1 by prince-canuma

 ยป  All LLMs  ยป  prince-canuma  ยป  Llama 3 6B V0.1   URL Share it on

  Arxiv:2212.05055   Arxiv:2404.08634   6b   Autotrain compatible Base model:finetune:prince-can... Base model:prince-canuma/llama...   Dataset:huggingfacefw/fineweb Dataset:prince-canuma/fineweb-...   En   Endpoints compatible   Llama   Llama-3-6b   Region:us   Safetensors   Sharded   Tensorflow

Llama 3 6B V0.1 Benchmarks

Llama 3 6B V0.1 (prince-canuma/Llama-3-6B-v0.1)

Llama 3 6B V0.1 Parameters and Internals

Model Type 
Llama
Use Cases 
Areas:
Research, Commercial applications
Applications:
Coding assistant, RAG, Function Calling and more
Limitations:
Limited scope for coding and math, Language limitations (English-only)
Additional Notes 
This model is created using downcycling from a larger model to reduce parameter size while maintaining performance.
Training Details 
Data Sources:
prince-canuma/fineweb-CC-MAIN-2024-10-1B-en, HuggingFaceFW/fineweb
Data Volume:
1B tokens
Methodology:
downcycling
Context Length:
8192
Hardware Used:
4x RTX 6000 using JarvisLabs
Input Output 
Input Format:
text input
Accepted Modalities:
text
Output Format:
text output
LLM NameLlama 3 6B V0.1
Repository ๐Ÿค—https://huggingface.co/prince-canuma/Llama-3-6B-v0.1 
Base Model(s)  Llama 3 6B V0   prince-canuma/Llama-3-6B-v0
Model Size6b
Required VRAM12.6 GB
Updated2025-01-12
Maintainerprince-canuma
Model Typellama
Model Files  5.0 GB: 1-of-3   5.0 GB: 2-of-3   2.6 GB: 3-of-3
Supported Languagesen
Model ArchitectureLlamaForCausalLM
Licensellama3
Context Length8192
Model Max Length8192
Transformers Version4.40.1
Tokenizer ClassPreTrainedTokenizerFast
Vocabulary Size128256
Torch Data Typefloat16

Best Alternatives to Llama 3 6B V0.1

Best Alternatives
Context / RAM
Downloads
Likes
Yi 6B 200K195K / 12.1 GB6822173
Yi 6B 200K AEZAKMI V2195K / 12.1 GB7071
Wukong Yi 6B 200K195K / 12.1 GB251
Yi 6B 200K DPO195K / 12.1 GB7990
Barcenas 6B 200K195K / 12.1 GB7672
Yi 6B 200K Llamafied195K / 12.1 GB1811
Yi 6B 200K Llama195K / 12.1 GB165
Chatglm2 6B Port Llama32K / 12.5 GB124
Miqu 6B Truthy31K / 11.3 GB2561
Pruned Llama 3 Oasis 6B8K / 13 GB281
Note: green Score (e.g. "73.2") means that the model is better than prince-canuma/Llama-3-6B-v0.1.

Rank the Llama 3 6B V0.1 Capabilities

๐Ÿ†˜ Have you tried this model? Rate its performance. This feedback would greatly assist ML community in identifying the most suitable model for their needs. Your contribution really does make a difference! ๐ŸŒŸ

Instruction Following and Task Automation  
Factuality and Completeness of Knowledge  
Censorship and Alignment  
Data Analysis and Insight Generation  
Text Generation  
Text Summarization and Feature Extraction  
Code Generation  
Multi-Language Support and Translation  

What open-source LLMs or SLMs are you in search of? 41250 in total.

Our Social Media →  
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241227